检索结果-内蒙古大学图书馆

2022 IEEE International Conference on robotics and Biomimetics, ROBIO 2022

作者： Li, Changle Zhang, Chentao Yu, Chuan You Zhang, Leifeng Liu, Gangfeng Zhao, Jie Harbin Institute of Technology State Key Laboratory of Robotics and System No.2 YiKuang Street NanGang District Harbin HeiLongJiang China

ISBN: (纸本)9781665481090

This paper presents a novel six-degree-of-freedom force feedback master manipulator for remote ultrasound scanning. Firstly, a new configuration based on a planar five-link mechanism is proposed, taking into account the practical needs of medical ultrasound scanning. This configuration has two operating modes and can provide three degrees of force feedback. Secondly, a hybrid force/position master-slave control system based on the kinetic model force feedback method is built, which can realize incremental master-slave control, variable proportional control, force feedback, and other functions. Finally, the positional accuracy, gravity balance effect, and force feedback performance of this master manipulator are verified through experiments. Experiments show that the average position error of this novel force feedback master manipulator is 1.18 mm, the average attitude error expressed in terms of Euler angles is 0.83°, and the maximum feedback force that can be provided is 12.1 N, which satisfies the requirements of ultrasonic scanning. © 2022 IEEE.

关键词： Feedback

来源：评论

学校读者我要写书评

暂无评论

A fast simulation method for magnetically driven deformation of a sheet micro soft robot 8

A fast simulation method for magnetically driven deformation...

引用

2022 8th International Conference on Mechanical Engineering, Materials and Automation technology, MMEAT 2022

作者： Gao, Jian Rong, Weibin Gao, Peng Li, Dongjie Wang, Lefeng State Key Laboratory of Robotics and System Harbin Institute of Technology Heilongjiang Harbin150001 China Key Laboratory of Advanced Manufacturing and Intelligent Technology Ministry of Education Harbin University of Science and Technology Heilongjiang Harbin150080 China

The magnetically driven micro soft robot is a hot research topic in the field of micro robotics. The magnetic torque of each part of the robot rotates with its deformation, so the magnetic torque and magnetic force to which the robot is subjected are difficult to be calculated directly. The lack of physical interfaces for torque distribution in many finite element software reduces the speed and accuracy of calculating the deformation of a robot using finite element simulation methods. In this paper, a fast simulation method to convert the local magnetic torque into equivalent load density for the deformation mode of the sheet micro soft robot is proposed. A finite element model of the fabricated micro soft robot is established, and the deformation and total magnetic moment of the robot under different magnetic field strength and magnetic field gradient are simulated and calculated. Experiments are executed to verify the validity of the simulation results. © Published under licence by IOP Publishing Ltd.

关键词： Robots

来源：评论

学校读者我要写书评

暂无评论

Design of Mixed Reality Assembly system Based on Improved ORB Algorithm 3

Design of Mixed Reality Assembly System Based on Improved OR...

引用

3rd International Conference on Computer Vision, Image and Deep Learning and International Conference on Computer Engineering and Applications, CVIDL and ICCEA 2022

作者： Lu, Na Xiao, YongFei Zhao, Jie Shandong Provincial Key Laboratory of Robot and Manufacturing Automation Technology ShanDong China Harbin Institute of Technology Institute of Automation Shandong State Key Laboratory of Robotics and System Harbin China

ISBN: (纸本)9781665459112

This paper studies the natural feature point detection algorithm in a virtual assembly system. To address the problems of unsatisfactory detection effect and poor matching accuracy of the ORB algorithm, a feature uniform distribution algorithm based on pyramidal grid division is proposed, and a strategy of retaining feature points according to Harris response values is formulated to solve the problem of feature point aggregation while ensuring extraction speed. Hamming distance and the RANSAC algorithm are used to constrain the matching results. The robot assembly system based on this algorithm overlays the 3D model of the spraying robot and virtual information in the mobile device to improve the assembly efficiency of the staff. The experimental results show that the mixed reality(MR) assembly system based on the algorithm of this paper performs well, and the real-time performance and alignment accuracy are improved. © 2022 IEEE.

关键词： Assembly

来源：评论

学校读者我要写书评

暂无评论

A Light Space Manipulator with High Load-to-Weight Ratio: system Development and Compliance Control

引用

Space(Science & technology) 2021年第1期2021卷 107-118页

作者： Zhiwei Wu Yongting Chen Wenfu Xu The School of Mechanical Engineering and Automation Harbin Institute of TechnologyShenzhen 518055China The State Key Laboratory of Robotics and System Harbin Institute of TechnologyHarbin 150001China

In order to meet the requirements of the space environment for the lightweight and load capacity of the manipulator,this paper designs a lightweight space manipulator with a weight of 9.23 kg and a load of 2 *** adopts the EtherCAT communication protocol and has the characteristics of high load-to-weight *** order to achieve constant force tracking under the condition of unknown environmental parameters,an integral adaptive admittance control method is *** control law is expressed as a third-order linear system equation,the operating environment is equivalent to a spring model,and the control error transfer function is *** control performance under the step response is further *** simulation results show that the proposed integral adaptive admittance control method has better performance than the traditional *** has no steady-state error,overcomes the problems caused by nonlinear discrete compensation,and can facilitate analysis in the frequency domain,realize parameter optimization,and improve calculation accuracy.

关键词： overcome load EtherCAT

来源：评论

学校读者我要写书评

暂无评论

HIT-Hawk and HIT-Phoenix: Two kinds of flapping-wing flying robotic birds with wingspans beyond 2 meters

引用

Biomimetic Intelligence & robotics 2021年第1期1卷 13-25页

作者： Erzhen Pan Hui Xu Han Yuan Jianqing Peng Wenfu Xu The School of Mechanical Engineering and Automation Harbin Institute of TechnologyShenzhen 518055China The State Key Laboratory of Robotics and System Harbin Institute of TechnologyHarbin 150001China

Inspired by large and medium-sized birds,two kinds of flapping-wing flying robots with wingspans beyond 2 meters were *** have the appearance of a hawk and a phoenix respectively,so they are called HIT-Hawk and *** this paper,the bionic concept,theoretical analysis,design and manufacturing are introduced in ***,the flight principle and characteristics of large and medium-sized birds were ***,the aerodynamics was modeled based on the thin airfoil theory,and the main design basis was ***,the mechanical structures of HIT-Hawk and HIT-Phoenix were designed to ensure the lateral and longitudinal stability and have optimized flight ***,an autonomous flight control method was proposed and realized in highly integrated on-onboard controller;it satisfies the strict restrictions on mass,size,power and ***,the prototypes were fabricated and verified through practical flight *** wingspans of these two flapping wing aircrafts are 2.0 m and 2.3 m respectively,the take-off weights are 1.15 kg and 0.86 kg,and the maximum stable endurance is 65 min(with battery of 3S LiPo,4300 mAh)and 8 min(with battery of 3S LiPo,800 mAh).Their wind resistance can both reach level *** with the small and micro flapping-wing aerial vehicles that mimic insects or small birds,they both have strong load capacity,strong wind resistance and long endurance.

关键词： Bionic robots Flapping-wing flying Unmanned aerial vehicle Robotic bird

来源：评论

学校读者我要写书评

暂无评论

A Time-Optimal Trajectory Planning Algorithm for Six-Degree-of-Freedom Robots Based on NURBS Curves

A Time-Optimal Trajectory Planning Algorithm for Six-Degree-...

引用

International Conference on Control, Automation and robotics (ICCAR)

作者： Hao Hong Minxiu Kong Jiawang Wang Qianjiang Wang School of Mechatronics Engineering Harbin Institute of Technology State Key Laboratory of Robotics and System Harbin China

ISBN: (数字)9798350373172

ISBN: (纸本)9798350373189

In this paper, we research and analyse the practical needs of robotic arm to complete the complex path planning of robotic arm and smooth transition of multi-attitude in the shortest time under the premise of satisfying the dynamics constraints, and put forward the time-optimal trajectory planning based on NURBS curves and multi-attitude interpolation algorithm based on quaternion with NURBS curves. Using the complex nature of quaternions, the quaternions are converted into three-dimensional space points for curve interpolation, and finally converted back to quaternions to achieve the second-order continuity of multi-gesture interpolation; a time-optimal trajectory planning algorithm based on NURBS curves is designed, which discretises the curves, and fits the NURBS curves using the discrete points. At the same time, the optimal rate solution under all the constraints is calculated point by point according to the discrete points on the motion path, and the optimal velocity curve satisfying the dynamics constraints is obtained, so as to achieve the time-optimal trajectory planning. Finally, the feasibility of the designed trajectory planning algorithm is verified in the simulation software and experimental platform, and it is proved that the algorithm can effectively improve the running speed by at least 30%.

关键词： Surface reconstruction Interpolation Trajectory planning Service robots Quaternions Heuristic algorithms Software algorithms

来源：评论

学校读者我要写书评

暂无评论

A WLS-Based Step-by-Step Identification Method for Industrial Robot Dynamics Parameters

A WLS-Based Step-by-Step Identification Method for Industria...

引用

International Conference on Control, Automation and robotics (ICCAR)

作者： Qianjiang Wang Mingxiu Kong Chuancheng Bian Hao Hong State Key Laboratory of Robotics and System School of Mechatronics Engineering Harbin Institute of Technology Harbin China

ISBN: (数字)9798350373172

ISBN: (纸本)9798350373189

In order to improve the accuracy of robot dynamics parameter identification, this paper designs a step-by-step identification method based on weighted least squares. The robot dynamics model is first linearized to obtain the minimum parameter set. Subsequently, the friction model is built separately and experiments are designed to recognize the joint friction parameters first. Based on this, the excitation trajectory of finite term Fourier series is designed and optimized and data are collected. The joint moments obtained from the difference between the overall experimentally collected moments and the calculated friction moments are used to obtain the complete robot dynamics parameters based on weighted least squares identification. Comparison of the designed overall identification experiments shows that the total moment residuals of this method are reduced by 35.52% compared with the one-time identification method, which proves the effectiveness of this method.

关键词： Parameter estimation Accuracy Automation Service robots Friction Industrial robots Kinetic theory

来源：评论

学校读者我要写书评

暂无评论

A Novel Gait Pattern Recognition Method Based on LSTM-CNN for Lower Limb Exoskeleton

引用

Journal of Bionic Engineering 2021年第5期18卷 1059-1072页

作者： Chao-feng Chen Zhi-jiang Du Long He Yong-jun Shi Jia-qi Wang Wei Dong State Key Laboratory of Robotics and System Harbin Institute of Technology(HIT)Harbin 150001China China South Industries Group Corporation Weapon Equipment Research InstituteBeijing 102202China

This paper describes a novel gait pattern recognition method based on Long Short-Term Memory(LSTM)and Convolutional Neural Network(CNN)for lower limb *** Inertial Measurement Unit(IMU)installed on the exoskeleton to collect motion information,which is used for LSTM-CNN *** article considers five common gait patterns,including walking,going up stairs,going down stairs,sitting down,and standing *** the LSTM-CNN model,the LSTM layer is used to process temporal sequences and the CNN layer is used to extract *** optimize the deep neural network structure proposed in this paper,some hyperparameter selection experiments were carried *** addition,to verify the superiority of the proposed recognition method,the method is compared with several common methods such as LSTM,CNN and *** results show that the average recognition accuracy can reach 97.78%,which has a good recognition eff ***,according to the experimental results of gait pattern switching,the proposed method can identify the switching gait pattern in time,which shows that it has good real-time performance.

关键词： Lower limb exoskeleton Gait pattern recognition LSTM-CNN Recognition accuracy Real-time performance

来源：评论

学校读者我要写书评

暂无评论

Squeezing More Past Knowledge for Online Class-Incremental Continual Learning

引用

IEEE/CAA Journal of Automatica Sinica 2023年第3期10卷 722-736页

作者： Da Yu Mingyi Zhang Mantian Li Fusheng Zha Junge Zhang Lining Sun Kaiqi Huang the State Key Laboratory of Robotics and System Harbin Institute of Technology(HIT)Harbin 150080China Center for Research on Intelligent System and Engineering Institute of AutomationChinese Academy of Sciences(CASIA)Beijing 100190 School of Artificial Intelligence University of Chinese Academy of SciencesBeijing 100049China Center for Research on Intelligent System and Engineering Institute of AutomationChinese Academy of Sciences(CASIA)Beijing 100190the School of Artificial IntelligenceUniversity of Chinese Academy of SciencesBeijing 100049 the CAS Center for Excellence in Brain Science and Intelligence Technology Shanghai 200031China IEEE

Continual learning(CL)studies the problem of learning to accumulate knowledge over time from a stream of data.A crucial challenge is that neural networks suffer from performance degradation on previously seen data,known as catastrophic forgetting,due to allowing parameter *** this work,we consider a more practical online class-incremental CL setting,where the model learns new samples in an online manner and may continuously experience new ***,prior knowledge is unavailable during training and *** works usually explore sample usages from a single dimension,which ignores a lot of valuable supervisory *** better tackle the setting,we propose a novel replay-based CL method,which leverages multi-level representations produced by the intermediate process of training samples for replay and strengthens supervision to consolidate previous ***,besides the previous raw samples,we store the corresponding logits and features in the ***,to imitate the prediction of the past model,we construct extra constraints by leveraging multi-level information stored in the *** the same number of samples for replay,our method can use more past knowledge to prevent *** conduct extensive evaluations on several popular CL datasets,and experiments show that our method consistently outperforms state-of-the-art methods with various sizes of episodic *** further provide a detailed analysis of these results and demonstrate that our method is more viable in practical scenarios.

关键词： Catastrophic forgetting class-incremental learning continual learning(CL) experience replay

来源：评论

学校读者我要写书评

暂无评论

A Novel Approach for Solving Time-Varying Linear Equations and Its Application in Motion Tracking of Redundant Robots

A Novel Approach for Solving Time-Varying Linear Equations a...

引用

Frontiers of robotics and Software Engineering (FRSE), International Conference on

作者： Hong Yin Hongzhe Jin Jie Zhao State Key Laboratory of Robotics and System Harbin Institute of Technology Harbin China

Solving time-varying linear equations is a common problem in many fields. In this article, a novel approach is proposed based on the cost function constructed by the mixed error, which is made up of the residual error and its integration. The merits of the novel approach include high accuracy, noise immunity, and asymptotic convergence. Since the derivative information of time-varying signals is used in the proposed method, a proportional-integral differentiator is designed based on the mixed estimation error for the first derivative estimation. The proposed differentiator has a high degree of precision, asymptotic convergence, and no chattering. In addition, theoretical analyses prove the convergence of the proposed optimal strategy and differentiator. Simulation results validate the effectiveness and superiority of the proposed strategy and the designed differentiator. Finally, the proposed approach is employed in the motion tracking of redundant robots.

关键词：

来源：评论

学校读者我要写书评

暂无评论

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案：

请选择收藏分类：

通借通还

建议与咨询 留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案： 新增检索档案 确定 取消

请选择收藏分类： 新增自定义分类 确定 取消

通借通还

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

请选择保存的检索档案：

请选择收藏分类：